Paper: Polarity Inducing Latent Semantic Analysis

ACL ID D12-1111
Title Polarity Inducing Latent Semantic Analysis
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2012

Existing vector space models typically map synonyms and antonyms to similar word vec- tors, and thus fail to represent antonymy. We introduce a new vector space representation where antonyms lie on opposite sides of a sphere: in the word vector space, synonyms have cosine similarities close to one, while antonyms are close to minus one. We derive this representation with the aid of a thesaurus and latent semantic analysis (LSA). Each entry in the thesaurus ? a word sense along with its synonyms and antonyms ? is treated as a ?document,? and the resulting doc- ument collection is subjected to LSA. The key contribution of this work is to show how to as- sign signs to the entries in the co-occurrence matrix on which LSA operates, so as to induce a subspace with the desired property. We evalua...